At present, image and video descriptors have been widely used in many computer vision applications. This paper presented a hierarchical multiscale texture-based image descriptor for image matching. The proposed descriptor utilizes mean values at multiscale levels of an image region to convert the image region to binary bitmaps and applies binary operations to effectively reduce the computational time and improve noise reduction to achieve stable and fast image matching. Experimental results show the high performance of our proposed method and robustness for object recognition over existing descriptors on image matching under variant illumination conditions.
